[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: mice experiment, risk for a clinical manifestation
Thank you very much for your suggestion.
> So there are two outcomes:
> 1. died of Z (how irritating to die of an irrelevant
> illness...) and
> 2. died of Y
> Simplest way to handle this is in a multinomial
> logistic regression
> with alive as the base category.
I see...I will try multinomial logistic.
By the way, mice and their immunological
conditions were monitored everyday.
Is this a sort of survival time data (?).
In addition, mice, which died of "Z", might
have developed "Y", if they have had survived
"Z". So, is it possible to treat
a death from "Z" as a "failure to follow up"
in whatever sort of survival analysis?
P.S. Let me apologise for the inadequate
remark about the death of mice.
Let's start Yahoo! Auction - Free Campaign Now!
* For searches and help try: